Product design loop for an existing Next.js/React app: define the problem, explore competing UX flows, validate the direction, prototype in the real codebase, and hand off a developer-ready behavior spec. Five skills, each usable alone, sharing one experiment record that keeps proposed, done, approved and unverified apart.
Plugin product-bridge from marketplace ccomkhj-skills in ccomkhj/skills. Commands read from the repo's manifest — 12 days ago.
pb-build-prototypeProductBridge stage 4. Build an isolated, reversible prototype of a chosen concept inside an authorized Next.js/React codebase, reusing its components and tokens and exercising loading, empty, error, success, responsive and keyboard behavior, then report exactly what was built and checked. Without r
pb-define-problemProductBridge stage 1. Frame a customer complaint or opportunity on an existing app as a problem brief that keeps observations, hypotheses and assumptions apart, with goals, constraints, candidate measures and open questions. Starts or resumes a .productbridge experiment. Use when a PM wants to defi
pb-developer-handoffProductBridge stage 5. Turn whatever exists (brief, chosen direction, real validation findings, prototype, or just a reviewed design) into a developer-ready behavior spec with scope, non-goals, flow, behavior by state, edge cases, Given/When/Then acceptance criteria, accessibility, instrumentation,
pb-explore-wireframesProductBridge stage 2. From a problem brief, explore two or three structurally different user flows for the same task, each with a hypothesis, key screens and states, trade-offs and open questions. Creates real design assets only when a tool actually does (Figma MCP when connected), otherwise a wire
pb-validate-directionProductBridge stage 3. Prepare neutral test tasks for competing concepts, or turn supplied customer notes, stakeholder comments and developer feasibility input into a source-traced evidence matrix and a decision record. Without real test data it writes only a research plan and the concepts stay unva
Goal-driven improvement loop: understand what needs improving, forge a /goal completion condition, then race a different-model Claude against Codex (each in its own git worktree) round by round until the goal is met, summarize, and ship a PR.
6 skills
Solo long-horizon goal loop: sharpen a spec (grill if vague), forge a /goal completion condition, then haul toward it turn after turn in a git worktree — each turn deciding explore (a fresh approach off the base) vs exploit (refine the incumbent), keeping only measured wins on a ratcheting incumbent branch, until the goal holds or the round cap trips. Then wrap up with a PR.
5 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.